<?xml version="1.0" standalone="yes"?>
<Paper uid="C96-1052">
  <Title>A Computational Model of Incremental Utterance Production in Task-Oriented Dialogues</Title>
  <Section position="4" start_page="0" end_page="304" type="intro">
    <SectionTitle>
2 Related Research
</SectionTitle>
    <Paragraph position="0"> Recent studies of human speech production (Levelt 1989) show that human speakers frequetatly use the incremental strategy of utterance production. This paper is concerned with a computational model of incremental utterance production. Computational models for the incremental syntactic formulation of a sentence were proposed (Kempen and HoenKamp 1987; De Smedt and Kempen 1991). Although incremental syntactic formulation is an important issue, we do not address this here.</Paragraph>
    <Paragraph position="1"> POPEL is a parallel and incremental natural language generation system (Finkler and Schauder 1992; Reithinger 1992). In POPEL, the &amp;quot;what to say&amp;quot; component determines the content to be generated and gradually carries it over to the &amp;quot;how to say&amp;quot; component, which formulates a sentence incrementally. POPEL can generate dis- null courses using eontextuM information, tlowever, it d(les not allow for the line structure ()f discourse prevailing in st)oken diMogues. We l)resent a eomlmtational model of incremental utterance l)roduetion using the line structure of discourse. Carletta, Caley, and Isard (1993) proi)osed an architecture for time-constrained la.nguage production. As for phenomena peculiar to st)oken dialogues, they focused on tlesil;C/Ltion an(l self-tel)air. Although our model ca,n 1)roduce filler terms and repair prior utterances, our chief concern is the tine structure of spoken discourse, which is closely related to incremental utterance pro(tnction.</Paragraph>
  </Section>
class="xml-element"></Paper>